RRLS : Robust Reinforcement Learning Suite

TL;DR

RRLS is a standardized benchmark suite based on Mujoco environments designed to evaluate robust reinforcement learning algorithms against environmental uncertainties, promoting reproducibility and comparability in research.

Contribution

This paper introduces RRLS, the first comprehensive benchmark suite for robust reinforcement learning, with six control tasks and two uncertainty sets, enhancing reproducibility and standardization.

Findings

Demonstrated RRLS's utility with recent algorithms

Provided a reproducible framework for robust RL evaluation

Facilitated comparison across different robust RL methods

Abstract

Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two types of uncertainty sets for training and evaluation. Our benchmark aims to standardize robust reinforcement learning tasks, facilitating reproducible and comparable experiments, in particular those from recent state-of-the-art contributions, for which we demonstrate the use of RRLS. It is also designed to be easily expandable to new environments. The source code is available at \href{https://github.com/SuReLI/RRLS}{https://github.com/SuReLI/RRLS}.